# Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systems

arXiv: https://arxiv.org/abs/2108.13592 · HTML: https://mlsanity.com/paper/2108.13592/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 31 Aug 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [Federated Meta-Learning with Fast Convergence and Efficient Communication](https://mlsanity.com/paper/1802.07876/) (2018)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings](https://mlsanity.com/paper/1904.11547/) (2019)
- [Addressing the Item Cold-start Problem by Attribute-driven Active Learning](https://mlsanity.com/paper/1805.09023/) (2018)
- [Security and Privacy on Blockchain](https://mlsanity.com/paper/1903.07602/) (2019)
- [From Zero-Shot Learning to Cold-Start Recommendation](https://mlsanity.com/paper/1906.08511/) (2019)
- [Recent Advances in Zero-shot Recognition](https://mlsanity.com/paper/1710.04837/) (2017)
- [Attribute-Guided Network for Cross-Modal Zero-Shot Hashing](https://mlsanity.com/paper/1802.01943/) (2018)
- [Learning to Recommend via Meta Parameter Partition](https://mlsanity.com/paper/1912.04108/) (2019)
- [From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation](https://mlsanity.com/paper/1906.04914/) (2019)

## Built on by (most cited first, 6 of 6)

- [Zero-Shot Recommendation as Language Modeling](https://mlsanity.com/paper/2112.04184/) (2021)
- [LLM-RecG: A Semantic Bias-Aware Framework for Zero-Shot Sequential Recommendation](https://mlsanity.com/paper/2501.19232/) (2025)
- [Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications](https://mlsanity.com/paper/2510.21131/) (2025)
- [Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems](https://mlsanity.com/paper/2309.01188/) (2023)
- [Bias-Eliminated Semantic Refinement for Any-Shot Learning](https://mlsanity.com/paper/2202.04827/) (2022)
- [A Systematic Evaluation and Benchmark for Embedding-Aware Generative Models: Features, Models, and Any-shot Scenarios](https://mlsanity.com/paper/2302.04060/) (2023)

## Abstract (arXiv)

User behavior has been validated to be effective in revealing personalized preferences for commercial recommendations. However, few user-item interactions can be collected for new users, which results in a null space for their interests, i.e., the cold-start dilemma. In this paper, a two-tower framework, namely, the model-agnostic interest learning (MAIL) framework, is proposed to address the cold-start recommendation (CSR) problem for recommender systems. In MAIL, one unique tower is constructed to tackle the CSR from a zero-shot view, and the other tower focuses on the general ranking task. Specifically, the zero-shot tower first performs cross-modal reconstruction with dual auto-encoders to obtain virtual behavior data from highly aligned hidden features for new users; and the ranking tower can then output recommendations for users based on the completed data by the zero-shot tower. Practically, the ranking tower in MAIL is model-agnostic and can be implemented with any embedding-based deep models. Based on the co-training of the two towers, the MAIL presents an end-to-end method for recommender systems that shows an incremental performance improvement. The proposed method has been successfully deployed on the live recommendation system of NetEase Cloud Music to achieve a click-through rate improvement of 13% to 15% for millions of users. Offline experiments on real-world datasets also show its superior performance in CSR. Our code is available.